arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.14038cs.CVcs.AI
收藏

资源高效的医学图像分析:基于自适应前向-前向网络

Resource-efficient Medical Image Analysis with Self-adapting Forward-Forward Networks

Friedrich–Alexander University Erlangen–Nürnberg(埃尔朗根-纽伦堡弗里德里希-亚历山大大学);Imperial College London(伦敦帝国学院)

Johanna P. Müller, Bernhard Kainz

AI总结:

提出SaFF-Net,一种基于卷积前向-前向算法和自适应参数微调的医学图像分析网络,在减少参数和计算的同时,性能可与反向传播网络竞争,尤其适用于一次性场景。

摘要:

我们提出了一种用于医学图像分析的快速自适应前向-前向网络(SaFF-Net),以缓解当前主要源于模型训练和微调中对反向传播的普遍依赖而导致的功耗和资源限制问题。基于最近提出的前向-前向算法(FFA),我们引入了卷积前向-前向算法(CFFA),这是一种参数高效的重新表述,适用于高级图像分析,并克服了原始FFA在速度和泛化方面的限制。为了解决FFA对超参数敏感的问题,我们还引入了一个自适应框架SaFF-Net,在预热和训练期间并行微调参数。我们的方法能够实现更有效的模型训练,并消除了FFA中先前对任意选择的Goodness函数的必要依赖。我们在多个基准数据集上评估了我们的方法,并与标准反向传播(BP)神经网络进行了比较,结果表明,基于FFA的网络在参数数量和函数评估次数显著减少的情况下,可以与标准模型竞争,尤其是在一次性场景和大批量情况下。代码将在会议期间提供。

英文摘要:

We introduce a fast Self-adapting Forward-Forward Network (SaFF-Net) for medical imaging analysis, mitigating power consumption and resource limitations, which currently primarily stem from the prevalent reliance on back-propagation for model training and fine-tuning. Building upon the recently proposed Forward-Forward Algorithm (FFA), we introduce the Convolutional Forward-Forward Algorithm (CFFA), a parameter-efficient reformulation that is suitable for advanced image analysis and overcomes the speed and generalisation constraints of the original FFA. To address hyper-parameter sensitivity of FFAs we are also introducing a self-adapting framework SaFF-Net fine-tuning parameters during warmup and training in parallel. Our approach enables more effective model training and eliminates the previously essential requirement for an arbitrarily chosen Goodness function in FFA. We evaluate our approach on several benchmarking datasets in comparison with standard Back-Propagation (BP) neural networks showing that FFA-based networks with notably fewer parameters and function evaluations can compete with standard models, especially, in one-shot scenarios and large batch sizes. The code will be available at the time of the conference.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑